This project aims to provide a comprehensive dataset and a powerful test bench model for speech summarization in the Persian language. The dataset and model are designed to facilitate research and development in the field of speech summarization while focusing on the unique characteristics of the Persian language.

The Persian Speech Summarization Dataset is a meticulously curated collection of speech data in Persian. It includes a diverse range of audio recordings covering informal speech domains, such as chichats, daily chats, calls, and more. With a wide range of topics and speakers, the dataset enables the training and evaluation of speech summarization algorithms for different use cases and scenarios.

Key features of the dataset:

• Large collection of Persian speech recordings
• Multiple voices and topics covered
• Rich metadata, including speaker information, recording details, transcripts, and more
• Fully annotated with high-quality summaries for each speech recording
• Segmented and aligned to facilitate model training and evaluation

This dataset is not currently accessible.

In addition to the dataset, we provide a high-performance Test Bench Model specifically tailored for the Persian language. The model is trained using state-of-the-art techniques in deep learning and natural language processing. It has been fine-tuned on the Persian Speech Summarization Dataset to optimize performance and accuracy.

Main features of the Test Bench Model:

• Built on advanced deep learning architectures
• Trained using large-scale Persian speech summarization data
• Utilizes cutting-edge natural language processing techniques
• High-quality, coherent summaries generated for Persian speech

To get a local copy up and running follow these simple example steps.

git clone https://github.com/example/repository.git

Install the necessary dependencies:

pip install -r requirements.txt

• Preprocess the dataset according to your specific requirements.
• Load the Test Bench Model and use it to generate summaries for Persian speech.

👤 Zahra

• GitHub: GitHub
• LinkedIn: LinkedIn

Contributions to the Persian Speech Summarization Dataset and Test Bench Model are welcome. If you would like to contribute to the project or provide feedback, please open an issue on the repository or submit a pull request.

Feel free to check the issues page.

Give a ⭐️ if you like this project!

This project is MIT licensed.